[R][NeurIPS 2020 Demo] Humans-in-the-loop molecule design UI with 50+ deep learning models!

Looks like an interesting tool but without traditional wet-lab experiments why should chemists believe your suggestions? While a good chemist can often come up with a reasonable explanation why a change helps after seeing changes in assay results (e.g. If you want to try get a compound made and tested perhaps contact the team at Covid Moonshot and see if there's a feasible use case. My PI (one of the leads) says they're always interested in new candidates/triage strategies. Another issue might be that the synthetic accessibility of your candidates after large numbers of augmentation steps may become low.